An evolutionary system for neural logic networks using genetic programming and indirect encoding

Nowadays, intelligent connectionist systems such as artificial neural networks have been proved very powerful in a wide area of applications. Consequently, the ability to interpret their structure was always a desirable feature for experts. In this field, the neural logic networks (NLN) by their definition are able to represent complex human logic and provide knowledge discovery. However, under contemporary methodologies, the training of these networks may often result in non-comprehensible or poorly designed structures. In this work, we propose an evolutionary system that uses current advances in genetic programming that overcome these drawbacks and produces neural logic networks that can be arbitrarily connected and are easily interpretable into expert rules. To accomplish this task, we guide the genetic programming process using a context-free grammar and we encode indirectly the neural logic networks into the genetic programming individuals. We test the proposed system in two problems of medical diagnosis. Our results are examined both in terms of the solution interpretability that can lead in knowledge discovery, and in terms of the achieved accuracy. We draw conclusions about the effectiveness of the system and we propose further research directions.     

The Effect of Dispositional Optimism in HRQOL in Patients with Chronic Musculoskeletal Pain Conditions in Greece

The purpose of this investigation was to study the influence of optimism in the quality of life of patients with musculoskeletal problems that were referred to Amfilohia Rehabilitation Center, because of chronic pain and kinetic difficulties. The sample consisted of 96 patients. The questionnaires that were used are the short form health questionnaire (12 questions; SF12), the life orientation test-revised (LOT-R) and a VAS scale for pain measurement. According to the regression analysis performed, dispositional optimism is an independent factor affecting both the physical (β = .249, p < .005) and mental composite score (β = .414, p < .0001) in patients with musculoskeletal problems, even after controlling for the effect of pain intensity.     

A method for the control of eating rate: A potential intervention in eating disorders

A method for the control of eating rate gave subjects feedback from a computer screen on how much and at what rate to eat during a meal. The method also allowed us to record the development of satiety during the meal. Linear eaters—that is, women selected for eating at an approximately constant rate—underate when challenged to eat at a lower rate and overate when challenged to eat at a higher rate, thereby modeling the eating behavior of patients with anorexia nervosa and binge eating disorder, respectively. In both cases, the women’s postmeal perception of satiety mimicked that of the respective patient group. The results provide support for the notion that linear eaters have the capacity to exhibit disordered eating.     

The Stability of the Five‐Factor Model of Personality in Personnel Selection and Assessment in Greece

The stability and replicability of the Five‐Factor model of personality across samples and testing purposes remain a significant issue in personnel selection and assessment. The present study explores the stability of a new Greek Big Five personality measure (TPQue) across different samples in order to explore the suitability of the measure in personnel selection and assessment. The factor structure of the measure across three samples (students, employees, and job applicants) is examined. The results of exploratory and confirmatory factor analyses show that the five‐factor structure remains intact for the students’, the applicants’ and the employees’ samples – contrary to previous studies – with all the sub‐scales of the personality measure (TPQue) loading on the intended factors. Furthermore, congruence coefficients between the samples justify the stability of the model in the working settings.     

A computerized test for the assessment of mild cognitive impairment subtypes in sentence processing

This study examines thesentence processing ability of mild cognitive impairment (MCI) subtypes. In addition to standard MCI neuropsychological tests, an experimental approach was applied to assess language. 133 people (93 MCI/40 controls) participated in novel computerized sentence processing tasks. Results presented statistically significant differences between MCI/controls andMCI subtypes (ANOVA):(a) duration F(2,92) = 19.259,p < .001) in sentence construction; (b) correct answers (F(2, 89) = 8.560,p < .001) and duration (F2,89) = 15.525,p < .001)in text comprehension; (c) correct answers (F(2, 92) = 8.975,p < .001) andduration (F(2, 92) = 4.360,p = .016) in metaphoric sentences comprehension; (d) correct answers (F(2, 92) = 12.836,p < .001) andduration (F(2, 92) = 10.974,p < .001) in verb form generation. Subtle changes in MCIsubtypes could affect sentence processing and provide useful information for cognitive decline risk estimation and screening purposes.     

Reducing uncertainty in sustainable interpersonal service relationships: the role of aesthetics

Sustainable interpersonal service relationships (SISRs) are the outcome of a design process that supports situated meaningful interactions between those being served and those in service. Service design is not just directed to simply satisfy the ability to perceive the psychological state of others, but more importantly, it should aim at preserving these relationships in relation to the contextual requirements that they functionally need, in order to be or remain sustainable. However, SISRs are uncertain since they have many possibilities to be in error in the sense that the constructed, situated meanings may finally be proven unsuccessful for the anticipations and the goals of those people engaged in a SISR. The endeavor of this paper is to show that aesthetic behavior plays a crucial role in the reduction of the uncertainty that characterizes such relationships. Aesthetic behavior, as an organized network of affective and cognitive processes, has an anticipatory evaluative function with a strong influence on perception by providing significance and value for those aspects in SISRs that exhibit many possibilities to serve goals that correspond to sustainable challenges. Thus, aesthetic behavior plays an important role in the construction of meanings that are related to both empathic and contextual aspects that constitute the entire situation in which a SISR takes place. Aesthetic behavior has a strong influence in meaning-making, motivating the selection of actions that contribute to our initial goal of interacting with uncertainty, to make the world a bit less puzzling and, thus, to improve our lives, or in other words, to design.     

Moral development and form of participation, type of sport, and sport experience

The present study investigated aspects of moral development in sport, according to the form of participation, type of sport, and sport experience. 510 participants, 14 to 49 years of age (M=24.9, SD=8.3) who came from organized competitive sports included athletes (n=327), referees (n=138), and coaches (n=45) in football (n = 161), handball (n = 198), and basketball (n = 150). Years of sport experience ranged from 1 to 6, 7 to 14, and 15 to 30 years of participation in sports. The Defining Issues Test was given; analysis showed no significant differences in development of moral reasoning among participants across different types of sports, forms of participation, and years of experience in sport.     

Judging the pleasantness of contour-rhythm-pitch-timbre musical combinations

The way people with various degrees of musical training integrate timbre, melodic contour, rhythm, and pitch information in an overall pleasantness judgment for musical excerpts was investigated. The theoretical and methodological framework of the study was the functional theory of cognition. In 2 experiments, participants were asked to attribute an overall pleasantness value to combinations of these factors. In Experiment 1, timbre, contour, rhythm, and overall pitch were manipulated. In Experiment 2, timbre and theme (a pattern of pitch and rhythm) were manipulated. Both experiments showed that in judging the pleasantness of musical combinations, participants apply a simple, additive rule in which the weight attributed to one element does not depend of the value of the other elements. Very few differences in regard to the combination rule were observed between participants with and without musical training. These results are discussed in reference to the controversy over pitch and rhythm interaction.     

An international comparative study of self-reported driver behavior

Using a large data base of 20,725 questionnaires from 19 European countries, this article uses a combination of factor analysis and tree based regression to determine driver groups with homogeneous self-reported behavior and determine whether regional differences in driving behaviors exist. Self-reported behavior, including speeding, reckless driving, seat belt use, and drinking and driving are examined. The results suggest that speeding and general reckless (dangerous) behavior are related, perhaps capturing a driver's “risk taking” or “pre-trip violations” behavior. Similarly, seat belt use and driving under the influence of alcohol are also related and may represent a driver's “law abiding” tendency or “during-trip violations” behavior. Further, important regional differences and similarities between European drivers are uncovered. Northern European drivers report a significantly higher compliance with drinking and driving laws and seat belt use regulations than do Southern and Eastern European drivers.     

Stochastic search item selection for factor analytic models

In this paper we implement a Markov chain Monte Carlo algorithm based on the stochastic search variable selection method of George and McCulloch (1993) for identifying promising subsets of manifest variables (items) for factor analysis models. The suggested algorithm is constructed by embedding in the usual factor analysis model a normal mixture prior for the model loadings with latent indicators used to identify not only which manifest variables should be included in the model but also how each manifest variable is associated with each factor. We further extend the suggested algorithm to allow for factor selection. We also develop a detailed procedure for the specification of the prior parameters values based on the practical significance of factor loadings using ideas from the original work of George and McCulloch (1993). A straightforward Gibbs sampler is used to simulate from the joint posterior distribution of all unknown parameters and the subset of variables with the highest posterior probability is selected. The proposed method is illustrated using real and simulated data sets.